LGMLNov 19, 2015

Predicting online user behaviour using deep learning algorithms

arXiv:1511.06247v353 citations
Originality Synthesis-oriented
AI Analysis

This work addresses predicting user behavior for e-commerce platforms, but it is incremental as it applies existing deep learning methods to a specific domain.

The authors tackled the problem of predicting user buying intentions on an e-commerce website by comparing traditional machine learning with deep learning methods, finding that Deep Belief Networks and Stacked Denoising Auto-Encoders achieved substantial improvements in handling high-dimensional data and class imbalance.

We propose a robust classifier to predict buying intentions based on user behaviour within a large e-commerce website. In this work we compare traditional machine learning techniques with the most advanced deep learning approaches. We show that both Deep Belief Networks and Stacked Denoising auto-Encoders achieved a substantial improvement by extracting features from high dimensional data during the pre-train phase. They prove also to be more convenient to deal with severe class imbalance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes